Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2102 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.7333. Min Act: -0.1700
Data Index: 8589732 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.6083. Min Act: -0.1700
Data Index: 4635470 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.5146. Min Act: -0.1700
Data Index: 986302 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.4833. Min Act: -0.1700
Data Index: 7705245 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.3583. Min Act: -0.1700
Data Index: 8457801 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.4208. Min Act: -0.1700
Data Index: 2754317 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.4208. Min Act: -0.1700
Data Index: 6388211 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.2958. Min Act: -0.1700
Data Index: 716062 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.3271. Min Act: -0.1700
Data Index: 1023092 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.2958. Min Act: -0.1700
Data Index: 8238289 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.2333. Min Act: -0.1700
Data Index: 2172618 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.2646. Min Act: -0.1700
Data Index: 5084241 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.2958. Min Act: -0.1700
Data Index: 5921888 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.2646. Min Act: -0.1700
Data Index: 4337250 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.2021. Min Act: -0.1700
Data Index: 846834 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.2333. Min Act: -0.1700
Data Index: 8223034 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.2021. Min Act: -0.1700
Data Index: 3307598 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.1708. Min Act: -0.1700
Data Index: 5619973 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.1396. Min Act: -0.1700
Data Index: 4359993 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7333. Min Range: -7.7333
Max Act: 7.1396. Min Act: -0.1700
Data Index: 1121457 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19